RomanNum3ral
/
scrapy
mirror of https://github.com/scrapy/scrapy.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Include extensions from #2067

This commit is contained in:
Adrián Chaves 2019-11-14 10:31:55 +01:00 committed by GitHub
parent 532770df52
commit be6da52019
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
scrapy/linkextractors/__init__.py
View File

@ -19,9 +19,12 @@ from scrapy.utils.url import (
# common file extensions that are not followed if they occur in links
IGNORED_EXTENSIONS = [
# archives
'7z', '7zip', 'bz2', 'rar', 'tar', 'tar.gz', 'xz', 'zip',
# images
'mng', 'pct', 'bmp', 'gif', 'jpg', 'jpeg', 'png', 'pst', 'psp', 'tif',
'tiff', 'ai', 'drw', 'dxf', 'eps', 'ps', 'svg',
'tiff', 'ai', 'drw', 'dxf', 'eps', 'ps', 'svg', 'cdr', 'ico',
# audio
'mp3', 'wma', 'ogg', 'wav', 'ra', 'aac', 'mid', 'au', 'aiff',
@ -35,7 +38,7 @@ IGNORED_EXTENSIONS = [
'odp',
# other
'css', 'pdf', 'exe', 'bin', 'rss', 'zip', 'rar', 'dmg', 'iso', 'apk', 'xz'
'css', 'pdf', 'exe', 'bin', 'rss', 'dmg', 'iso', 'apk'
]